Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data | NSF Public Access Repository

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Citation Details

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data

Award ID(s):: 2031883 2023505

PAR ID:: 10344164

Author(s) / Creator(s):: Frei, Spencer; Chatterji, Niladri; Bartlett, Peter L.

Date Published:: 2022-01-01

Journal Name:: Proceedings of the 35th Conference on Learning Theory (COLT2022)

Format(s):: Medium: X

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
Accepted Manuscript1.0
Conference Paper:
The DOI is not currently available.